CodeTracer: Towards Traceable Agent States

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation hard to observe. In these runs, an early misstep can trap the agent in unproductive loops or even cascade into fundamental errors, forming hidden error chains that make it hard to tell when the agent goes off track and why. Existing agent tracing analyses either focus on simple interaction or rely on small-scale manual inspection, which limits their scalability and usefulness for real coding workflows. We present CodeTracer, a tracing architecture that parses heterogeneous run artifacts through evolving extractors, reconstructs the full state transition history as a hierarchical trace tree with persistent memory, and performs failure onset localization to pinpoint the failure origin and its downstream chain. To enable systematic evaluation, we construct CodeTraceBench from a large collection of executed trajectories generated by four widely used code agent frameworks on diverse code tasks (e.g., bug fixing, refactoring, and terminal interaction), with supervision at both the stage and step levels for failure localization. Experiments show that CodeTracer substantially outperforms direct prompting and lightweight baselines, and that replaying its diagnostic signals consistently recovers originally failed runs under matched budgets. Our code and data are publicly available.

The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results

This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural and realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. Performance is evaluated using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 96 registrants, with 10 teams submitting valid models; ultimately, 9 teams achieved valid scores in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?

Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Expansion (open-web search). However, existing evaluations fall short: they lack flexible tool integration, test visual and search tools separately, and evaluate primarily by final answers. Consequently, they cannot verify if tools were actually invoked, applied correctly, or used efficiently. To address this, we introduce Agentic-MME, a process-verified benchmark for Multimodal Agentic Capabilities. It contains 418 real-world tasks across 6 domains and 3 difficulty levels to evaluate capability synergy, featuring over 2,000 stepwise checkpoints that average 10+ person-hours of manual annotation per task. Each task includes a unified evaluation framework supporting sandboxed code and APIs, alongside a human reference trajectory annotated with stepwise checkpoints along dual-axis: S-axis and V-axis. To enable true process-level verification, we audit fine-grained intermediate states rather than just final answers, and quantify efficiency via an overthinking metric relative to human trajectories. Experimental results show the best model, Gemini3-pro, achieves 56.3% overall accuracy, which falls significantly to 23.0% on Level-3 tasks, underscoring the difficulty of real-world multimodal agentic problem solving.

ContextBench: A Benchmark for Context Retrieval in Coding Agents

LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks. Data and code are available at: https://cioutn.github.io/context-bench/.

LongCat-Flash-Thinking-2601 Technical Report

We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thinking-2601 achieves state-of-the-art performance among open-source models on a wide range of agentic benchmarks, including agentic search, agentic tool use, and tool-integrated reasoning. Beyond benchmark performance, the model demonstrates strong generalization to complex tool interactions and robust behavior under noisy real-world environments. Its advanced capability stems from a unified training framework that combines domain-parallel expert training with subsequent fusion, together with an end-to-end co-design of data construction, environments, algorithms, and infrastructure spanning from pre-training to post-training. In particular, the model's strong generalization capability in complex tool-use are driven by our in-depth exploration of environment scaling and principled task construction. To optimize long-tailed, skewed generation and multi-turn agentic interactions, and to enable stable training across over 10,000 environments spanning more than 20 domains, we systematically extend our asynchronous reinforcement learning framework, DORA, for stable and efficient large-scale multi-environment training. Furthermore, recognizing that real-world tasks are inherently noisy, we conduct a systematic analysis and decomposition of real-world noise patterns, and design targeted training procedures to explicitly incorporate such imperfections into the training process, resulting in improved robustness for real-world applications. To further enhance performance on complex reasoning tasks, we introduce a Heavy Thinking mode that enables effective test-time scaling by jointly expanding reasoning depth and width through intensive parallel thinking.

T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation

Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet its evaluation remains fragmented, often relying on unimodal metrics or narrowly scoped benchmarks that fail to capture cross-modal alignment, instruction following, and perceptual realism under complex prompts. To address this limitation, we present T2AV-Compass, a unified benchmark for comprehensive evaluation of T2AV systems, consisting of 500 diverse and complex prompts constructed via a taxonomy-driven pipeline to ensure semantic richness and physical plausibility. Besides, T2AV-Compass introduces a dual-level evaluation framework that integrates objective signal-level metrics for video quality, audio quality, and cross-modal alignment with a subjective MLLM-as-a-Judge protocol for instruction following and realism assessment. Extensive evaluation of 11 representative T2AVsystems reveals that even the strongest models fall substantially short of human-level realism and cross-modal consistency, with persistent failures in audio realism, fine-grained synchronization, instruction following, etc. These results indicate significant improvement room for future models and highlight the value of T2AV-Compass as a challenging and diagnostic testbed for advancing text-to-audio-video generation.

Meeseeks: An Iterative Benchmark Evaluating LLMs Multi-Turn Instruction-Following Ability

The ability to follow instructions accurately is fundamental for Large Language Models (LLMs) to serve as reliable agents in real-world applications. While existing instruction-following benchmarks are either single-turn or introduce new requirements in each turn without allowing self-correction, Meeseeks simulates realistic human-LLM interactions through an iterative feedback process. This design enables models to self-correct based on specific requirement failures, better reflecting real-world user-end usage patterns. The benchmark implements a comprehensive evaluation system with 38 capability tags organized across three dimensions: Intent Recognition, Granular Content Validation, and Output Structure Validation. Through rigorous evaluation across LLMs, Meeseeks provides valuable insights into LLMs' instruction-following capabilities in practical applications.

Training-free Task-oriented Grasp Generation

This paper presents a training-free pipeline for task-oriented grasp generation that combines pre-trained grasp generation models with vision-language models (VLMs). Unlike traditional approaches that focus solely on stable grasps, our method incorporates task-specific requirements by leveraging the semantic reasoning capabilities of VLMs. We evaluate five querying strategies, each utilizing different visual representations of candidate grasps, and demonstrate significant improvements over a baseline method in both grasp success and task compliance rates, with absolute gains of up to 36.9% in overall success rate. Our results underline the potential of VLMs to enhance task-oriented manipulation, providing insights for future research in robotic grasping and human-robot interaction.

ParseCaps: An Interpretable Parsing Capsule Network for Medical Image Diagnosis

Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing this issue. Nevertheless, traditional capsule networks often underperform due to their shallow structures, and deeper variants lack hierarchical architectures, thereby compromising interpretability. This paper introduces a novel capsule network, ParseCaps, which utilizes the sparse axial attention routing and parse convolutional capsule layer to form a parse-tree-like structure, enhancing both depth and interpretability. Firstly, sparse axial attention routing optimizes connections between child and parent capsules, as well as emphasizes the weight distribution across instantiation parameters of parent capsules. Secondly, the parse convolutional capsule layer generates capsule predictions aligning with the parse tree. Finally, based on the loss design that is effective whether concept ground truth exists or not, ParseCaps advances interpretability by associating each dimension of the global capsule with a comprehensible concept, thereby facilitating clinician trust and understanding of the model's classification results. Experimental results on CE-MRI, PH$^2$, and Derm7pt datasets show that ParseCaps not only outperforms other capsule network variants in classification accuracy, redundancy reduction and robustness, but also provides interpretable explanations, regardless of the availability of concept labels.

OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning

Redundancy is a persistent challenge in Capsule Networks (CapsNet),leading to high computational costs and parameter counts. Although previous works have introduced pruning after the initial capsule layer, dynamic routing's fully connected nature and non-orthogonal weight matrices reintroduce redundancy in deeper layers. Besides, dynamic routing requires iterating to converge, further increasing computational demands. In this paper, we propose an Orthogonal Capsule Network (OrthCaps) to reduce redundancy, improve routing performance and decrease parameter counts. Firstly, an efficient pruned capsule layer is introduced to discard redundant capsules. Secondly, dynamic routing is replaced with orthogonal sparse attention routing, eliminating the need for iterations and fully connected structures. Lastly, weight matrices during routing are orthogonalized to sustain low capsule similarity, which is the first approach to introduce orthogonality into CapsNet as far as we know. Our experiments on baseline datasets affirm the efficiency and robustness of OrthCaps in classification tasks, in which ablation studies validate the criticality of each component. Remarkably, OrthCaps-Shallow outperforms other Capsule Network benchmarks on four datasets, utilizing only 110k parameters, which is a mere 1.25% of a standard Capsule Network's total. To the best of our knowledge, it achieves the smallest parameter count among existing Capsule Networks. Similarly, OrthCaps-Deep demonstrates competitive performance across four datasets, utilizing only 1.2% of the parameters required by its counterparts.